|
Seeing n_best predictions while decoding
|
|
1
|
1138
|
April 19, 2021
|
|
Parameter Sharing across Layers in Transformers
|
|
0
|
1608
|
April 27, 2023
|
|
How to compare two testsets
|
|
1
|
1135
|
March 16, 2021
|
|
Translating names issue
|
|
1
|
1135
|
July 22, 2020
|
|
How to compile ctranslate2 so as to run converted marian models w/ MKL on CPU
|
|
0
|
1595
|
December 2, 2024
|
|
NMTWizard recommendations?
|
|
1
|
1120
|
January 13, 2020
|
|
Pretrained Catalan OpenNMT models
|
|
0
|
1580
|
November 24, 2022
|
|
Seeking to install opennmt-py on Windows
|
|
1
|
1117
|
May 22, 2023
|
|
Converter: Hints for converting Transformer of GPTBigCodeForCausalLM
|
|
1
|
1114
|
May 26, 2023
|
|
How to determine alignments accuracy?
|
|
0
|
1571
|
April 5, 2019
|
|
How to go about recreating a basic seq2seq model
|
|
0
|
1569
|
November 16, 2020
|
|
What preprocesstions are needed when training english->chinese model?
|
|
0
|
1569
|
February 5, 2018
|
|
Using pretrained embeddings for additional features
|
|
1
|
1109
|
January 22, 2019
|
|
Using BART-mnli with CTranslate2
|
|
1
|
1107
|
May 24, 2023
|
|
Using Tree Bases Source Data for MT Task in OpenNMT-py
|
|
1
|
1107
|
August 4, 2020
|
|
Is Data Checkpointing possible?
|
|
1
|
1104
|
July 7, 2023
|
|
Hybrid model training
|
|
1
|
1104
|
June 10, 2020
|
|
Need support for training russian -> chinese model
|
|
0
|
1559
|
February 5, 2018
|
|
Log_file encoding
|
|
1
|
1101
|
June 2, 2021
|
|
Is Tokenizer::tokenize() thread-safe
|
|
0
|
1556
|
December 14, 2023
|
|
Problem running script with Glove embeddings
|
|
1
|
1100
|
November 26, 2020
|
|
Using pretrained En-De model?
|
|
1
|
1101
|
September 3, 2018
|
|
Training Progress
|
|
1
|
1099
|
January 3, 2022
|
|
Github repo to translate from Tibetan to English with Google Colab
|
|
0
|
1554
|
June 17, 2024
|
|
BLEU score is being 0
|
|
0
|
1552
|
July 1, 2018
|
|
M2m100 Out-of-Vocabulary
|
|
0
|
1548
|
December 29, 2024
|
|
((withdrawn by author))
|
|
1
|
1090
|
June 17, 2021
|
|
Ctranslate2 Support for DeltaLM
|
|
1
|
1088
|
June 22, 2023
|
|
Export saved_model with tflite mode
|
|
0
|
1537
|
September 22, 2023
|
|
A (potential) bug of the field of indices of batch
|
|
0
|
1533
|
August 3, 2018
|
|
Train new SPM model for additional training
|
|
0
|
1532
|
December 18, 2023
|
|
Running ct2-marian-converter converted marian model on cpu
|
|
0
|
1525
|
November 27, 2024
|
|
Weird output when translate
|
|
1
|
1078
|
October 8, 2018
|
|
Scores returned by TF model server
|
|
1
|
1077
|
March 22, 2019
|
|
OpenNMT-py full documentation link broken
|
|
1
|
1077
|
February 17, 2019
|
|
Parameters inquiry: train_steps, queue_size, bucket_size
|
|
0
|
1523
|
September 16, 2021
|
|
Influence of the parameter "number of heads" on the size of the model
|
|
1
|
1076
|
July 26, 2023
|
|
Target case - OpenNMT-py
|
|
0
|
1518
|
June 1, 2018
|
|
Model specification
|
|
0
|
1514
|
December 23, 2016
|
|
Zero learning rate
|
|
1
|
1068
|
December 17, 2019
|
|
Target tokens out of vocabulary
|
|
1
|
1064
|
April 3, 2023
|
|
Error while Training using share-vocab
|
|
1
|
1064
|
January 30, 2021
|
|
CJK tokenizer question
|
|
0
|
1504
|
May 12, 2017
|
|
Why there are spaces in ".tmp.pred.txt" file - evaluate_bleu.py (LUA model im2text)
|
|
0
|
1502
|
April 22, 2021
|
|
Preprocess argument "-filter_valid" - what does it mean?
|
|
1
|
1064
|
November 30, 2019
|
|
If NMT rest_translation_server supports concurrent access
|
|
0
|
1498
|
September 13, 2017
|
|
Multimodal: initialize hidden state of encoder + transformer
|
|
0
|
1493
|
November 2, 2020
|
|
ValueError: shuffle_buffer_size < 0 is not compatible with weighted datasets
|
|
1
|
1054
|
June 13, 2023
|
|
Training.lua as a library
|
|
0
|
1481
|
December 23, 2016
|
|
Cannot initialize Translator class object
|
|
1
|
1044
|
November 9, 2020
|